Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ormal
    1.09
    Pa
    1.05
    winfo
    1.05
    bmatrix
    1.04
     toBe
    1.01
    Ł
    1.01
    Ex
    1.00
     Pati
    0.99
     새
    0.99
     معا
    0.99
    POSITIVE LOGITS
    ار
    1.14
    лар
    1.14
    旗
    1.14
     contender
    1.12
    ayu
    1.12
    􀂃
    1.12
     playthrough
    1.12
    湖
    1.12
    𝖐
    1.10
     CFT
    1.09
    Act Density 0.000%

    No Known Activations